SUper Team at SemEval-2016 Task 3: Building a feature-rich system for community question answering
This work addresses community question answering for users of forums, but it is incremental as it combines existing feature types without introducing a new method.
The researchers tackled the problem of community question answering by building a feature-rich system for SemEval-2016 Task 3, achieving best results on subtask C and strong results on subtasks A and B.
We present the system we built for participating in SemEval-2016 Task 3 on Community Question Answering. We achieved the best results on subtask C, and strong results on subtasks A and B, by combining a rich set of various types of features: semantic, lexical, metadata, and user-related. The most important group turned out to be the metadata for the question and for the comment, semantic vectors trained on QatarLiving data and similarities between the question and the comment for subtasks A and C, and between the original and the related question for Subtask B.